面向超宽带室内定位的FCM-SSGP方法

doi:10.19678/j.issn.1000-3428.0063921

摘要/Abstract

摘要： 受室内墙壁、玻璃、木门等障碍物影响，UWB室内定位中UWB信号的传播环境变为非视距环境，在该环境下定位将极大降低定位精度。现有抑制NLOS误差的方法由于复杂度较大导致定位时间过长，结合模糊C均值（FCM）聚类及稀疏谱高斯过程回归（SSGP）方法，提出一种FCM-SSGP定位方法。对接收到的信道冲击响应信号提取特征，利用FCM聚类识别NLOS信号，并根据NLOS信号传播环境的恶劣程度将NLOS信号划分为轻度NLOS信号和一般NLOS信号。使用SSGP方法分别得到2个不同信道条件下的NLOS误差，将SSGP方法得到的测距误差与FCM聚类得到的隶属度相结合作为权值，以抑制NLOS误差。实验结果表明，FCM-SSGP方法能有效降低不同障碍物带来的NLOS误差，定位误差为21.01 cm，与LS-SVM及SPGP方法相比，其定位误差均值分别提升了8.23 cm和6.73 cm，定位所需时间相比LSTM方法缩短了9.35倍，在保证高定位精度的同时降低了计算复杂度。

关键词: 非视距抑制, 非视距识别, 模糊C均值, 稀疏谱高斯过程, 超宽带定位

Abstract: Obstacles such as indoor walls, glass, and wooden doors influence the propagation environment of Ultra-Wideband(UWB) signals in UWB indoor positioning, and the environment becomes a Non-Line-of-Sight(NLOS) environment, in which positioning considerably reduces positioning accuracy.Existing methods to mitigate NLOS errors take too long to locate due to the complexity.This paper presents a positioning method that combines Fuzzy C-Means (FCM) clustering and Sparse Spectral Gaussian Process(SSGP) regression and is named FCM-SSGP.The characteristics of the received channel impact response signal are determined, and FCM clustering is used to identify the NLOS signal and divide this signal into mild and general NLOS signals depending on the severity of the NLOS signal propagation environment.The NLOS errors under two different channel conditions are obtained by using the SSGP method.The ranging errors obtained by combining the SSGP method with the membership degree obtained by applying FCM clustering are used as weights to alleviate the NLOS errors.The results show that the FCM-SSGP method can effectively reduce the NLOS error caused by different obstacles, achieving a positioning error of 21.01 cm.The mean value of positioning error is improved by 8.23 cm and 6.73 cm compared with those of the LS-SVM and SPGP methods, respectively, and the time required for positioning is reduced by 9.35 times that of the LSTM method.This method ensures high positioning accuracy and reduces computational complexity.

Key words: Non-Line of Sight (NLOS) mitigation, NLOS identification, Fuzzy C-Means(FCM) clustering, Sparse Spectral Gaussian Process(SSGP) regression, Ultra-Wideband(UWB) localization

中图分类号:

TP391

张盛, 唐帆, 张天骐, 范森. 面向超宽带室内定位的FCM-SSGP方法[J]. 计算机工程, 2023, 49(3): 211-220.

ZHANG Sheng, TANG Fan, ZHANG Tianqi, FAN Sen. FCM-SSGP Method for Ultra-Wideband Indoor Localization[J]. Computer Engineering, 2023, 49(3): 211-220.

https://www.ecice06.com/CN/Y2023/V49/I3/211

图/表 18

20230314185914

20230314185917

20230314185920

20230314185924

20230314185935

20230314185938

20230314185942

20230314185945

20230314185948

20230314185951

20230314185954

20230314185958

20230314190001

20230314190004

20230314190007

20230314190011

20230314190015

20230314190019

参考文献

[1] ZAFARI F, GKELIAS A, LEUNG K K.A survey of indoor localization systems and technologies[J].IEEE Communications Surveys & Tutorials, 2019, 21(3):2568-2599.
[2] JIMÉNEZ RUIZ A R, SECO GRANJA F.Comparing ubisense, BeSpoon, and DecaWave UWB location systems:indoor performance analysis[J].IEEE Transactions on Instrumentation and Measurement, 2017, 66(8):2106-2117.
[3] WANG W, WANG G, ZHANG J, et al.Robust weighted least squares method for TOA-based localization under mixed LOS/NLOS conditions[J].IEEE Communications Letters, 2017, 21(10):2226-2229.
[4] 杨刚, 朱士玲, 李强, 等.融合UWB与INS的消防员室内定位与NLOS检测算法[J].计算机工程, 2021, 47(9):153-161. YANG G, ZHU S L, LI Q, et al.Indoor firefighter positioning and NLOS detection algorithm based on UWB and INS[J].Computer Engineering, 2021, 47(9):153-161.(in Chinese)
[5] MUQAIBEL A H, LANDOLSI M A, MAHMOOD M N.Practical evaluation of NLOS/LOS parametric classification in UWB channels[C]//Proceedings of the 1st International Conference on Communications, Signal Processing, and their Applications.Washington D.C., USA:IEEE Press, 2013:1-6.
[6] KRISTENSEN J B, MASSANET GINARD M, JENSEN O K, et al.Non-line-of-sight identification for UWB indoor positioning systems using support vector machines[C]//Proceedings of IEEE MTT-S International Wireless Symposium.Washington D.C., USA:IEEE Press, 2019:1-3.
[7] BREGAR K, HROVAT A, MOHORI M.NLOS channel detection with multilayer perceptron in low-rate personal area networks for indoor localization accuracy improvement[C]//Proceedings of the 8th Jožef Stefan International Postgraduate School Student Conference.Ljubljana, Slovenia:Jožef Stefan Institute, 2016:1-5.
[8] MUSA A, NUGRAHA G D, HAN H, et al.A decision tree-based NLOS detection method for the UWB indoor location tracking accuracy improvement[J].International Journal of Communication Systems, 2019, 32(13):39-97.
[9] MARANÒ S, GIFFORD W M, WYMEERSCH H, et al.NLOS identification and mitigation for localization based on UWB experimental data[J].IEEE Journal on Selected Areas in Communications, 2010, 28(7):1026-1035.
[10] 王斐, 徐湛, 职如昕, 等.基于卷积神经网络的OFDM-UWB信道环境识别[J].计算机工程, 2021, 47(7):161-167. WANG F, XU Z, ZHI R X, et al.OFDM-UWB channel environment recognition based on convolutional neural network[J].Computer Engineering, 2021, 47(7):161-167.(in Chinese)
[11] YU K G, WEN K, LI Y B, et al.A novel NLOS mitigation algorithm for UWB localization in harsh indoor environments[J].IEEE Transactions on Vehicular Technology, 2019, 68(1):686-699.
[12] WU S H, MA Y K, ZHANG Q Y, et al.NLOS error mitigation for UWB ranging in dense multipath environments[C]//Proceedings of IEEE Wireless Communications and Networking Conference.Washington D.C., USA:IEEE Press, 2007:1565-1570.
[13] WYMEERSCH H, MARANO S, GIFFORD W M, et al.A machine learning approach to ranging error mitigation for UWB localization[J].IEEE Transactions on Communications, 2012, 60(6):1719-1728.
[14] BARRAL V, ESCUDERO C J, GARCÍA-NAYA J A, et al.NLOS identification and mitigation using low-cost UWB devices[J].Sensors (Basel, Switzerland), 2019, 19(16):3464-3473.
[15] CHEN Y Y, HUANG S P, WU T W, et al.UWB system for indoor positioning and tracking with arbitrary target orientation, optimal anchor location, and adaptive NLOS mitigation[J].IEEE Transactions on Vehicular Technology, 2020, 69(9):9304-9314.
[16] YANG X F.NLOS mitigation for UWB localization based on sparse pseudo-input Gaussian process[J].IEEE Sensors Journal, 2018, 18(10):4311-4316.
[17] LÁZARO-GREDILLA M, CANDELA J Q, RASMUSSEN C, et al.Sparse spectrum Gaussian process regression[J].Journal of Machine Learning Research, 2010, 11:1865-1881.
[18] ABBASI A, LIU H P.Novel cascade CNN algorithm for UWB signal denoising, compressing, and ToA estimation[C]//Proceedings of the 11th Annual Computing and Communication Workshop and Conference.Washington D.C., USA:IEEE Press, 2021:721-725.
[19] LANDOLSI M A, ALMUTAIRI A F, KOURAH M A.LOS/NLOS channel identification for improved localization in wireless ultra-wideband networks[J].Telecommunication Systems, 2019, 72(3):441-456.
[20] WANG F, XU Z, ZHI R X, et al.LOS/NLOS channel identification technology based on CNN[C]//Proceedings of the 6th NAFOSTED Conference on Information and Computer Science (NICS).Washington D.C., USA:IEEE Press, 2019:200-203.
[21] ZENG Z Q, LIU S, WANG L.UWB NLOS identification with feature combination selection based on genetic algorithm[C]//Proceedings of 2019 IEEE International Conference on Consumer Electronics.Washington D.C., USA:IEEE Press, 2019:1-5.
[22] RASMUSSEN C E, WILLIAMS C K I.Gaussian processes for machine learning[EB/OL].[2021-01-02].https://www.researchgate.net/publication/41781559_Gaussian_Process_for_Machine_Learning.
[23] PARK S H, BAE Y B, FIDAN B, et al.Distance-based mobile node localization of fixed beacons using RMS prop[C]//Proceedings of the 58th Annual Conference of the Society of Instrument and Control Engineers of Japan.Washington D.C., USA:IEEE Press, 2019:376-381.
[24] YANG S W, WANG B.Residual based weighted least square algorithm for bluetooth/UWB indoor localization system[C]//Proceedings of the 36th Chinese Control Conference.Washington D.C., USA:IEEE Press, 2017:5959-5963.

选择文件类型/文献管理软件名称

选择包含的内容